Shima Soleimani; Omid Bozorg Haddad; Mojtaba Moravej
Abstract
Introduction: Surface water bodies are the most easily available water resources. Increase use and waste water withdrawal of surface water causes drastic changes in surface water quality. Water quality, importance as the most vulnerable and important water supply resources is absolutely clear. Unfortunately, ...
Read More
Introduction: Surface water bodies are the most easily available water resources. Increase use and waste water withdrawal of surface water causes drastic changes in surface water quality. Water quality, importance as the most vulnerable and important water supply resources is absolutely clear. Unfortunately, in the recent years because of city population increase, economical improvement, and industrial product increase, entry of pollutants to water bodies has been increased. According to that water quality parameters express physical, chemical, and biological water features. So the importance of water quality monitoring is necessary more than before. Each of various uses of water, such as agriculture, drinking, industry, and aquaculture needs the water with a special quality. In the other hand, the exact estimation of concentration of water quality parameter is significant.
Material and Methods: In this research, first two input variable models as selection methods (namely, correlation coefficient and principal component analysis) were applied to select the model inputs. Data processing is consisting of three steps, (1) data considering, (2) identification of input data which have efficient on output data, and (3) selecting the training and testing data. Genetic Algorithm-Least Square Support Vector Regression (GA-LSSVR) algorithm were developed to model the water quality parameters. In the LSSVR method is assumed that the relationship between input and output variables is nonlinear, but by using a nonlinear mapping relation can create a space which is named feature space in which relationship between input and output variables is defined linear. The developed algorithm is able to gain maximize the accuracy of the LSSVR method with auto LSSVR parameters. Genetic algorithm (GA) is one of evolutionary algorithm which automatically can find the optimum coefficient of Least Square Support Vector Regression (LSSVR). The GA-LSSVR algorithm was employed to model water quality parameters such as Na+, K+, Mg2+, So42-, Cl-, pH, Electric conductivity (EC) and total dissolved solids (TDS) in the Sefidrood River. For comparison the selected input variable methods coefficient of determination (R2), root mean square error (RMSE), and Nash-Sutcliff (NS) are applied.
Results and Discussion: According to Table 5, the results of the GA-LSSVR algorithm by using correlation coefficient and PCA methods approximately show similar results. About pH, EC, and TDS quality parameters, the results of PCA method have, the more accuracy, but the difference of RMSE between the PCA method and correlation coefficient method is not significant. The PCA method cause improvement in NS values to 22 and 0.1 percentages in pH and TDS water quality parameters to the correlation coefficient method, respectively,and NS criteria value for EC water quality parameter did not change in both methods. As a result, according to positive values of NS criteria in both PCA and correlation methods, it is clear that GA-LSSVR has a high ability for modeling of water quality parameters. Because of summation of NS criteria for PCA method is 5.53 and for correlation coefficient is 5.62, we can say that the correlation coefficient method has more applicable as a data processing method, but both methods have a high ability. Orouji et all. (18) used assumed models to model Na+, K+, Mg2+, So42- , Cl- , pH, EC, and TDS by Genetic programming (GP) method. The RMSE criteria of the better models for testing data are 2.1, 0.02, 0.85, 0.93, 2.18, 0.33, 404.15, and 246.15, respectively. For comparison the orouji et al. (18) and table (5), the Results show using the correlation coefficient method as a data processing method can improve the results to 5.5 times. The results indicate the superiority of developingalgorithm increases the modeling accuracy. It is worth mentioning that according to NS criteria both selected inputs variable methods (correlation coefficient and PCA) are capable to model the water quality parameters. Also the result shows that using correlation coefficient method lead to more accurate results than PCA.
Conclusion: In this study, GA algorithm as one of the most applicable optimization algorithms in the different sciences was used to optimize the LSSVR coefficients and Then GA-LSSVR was developed to model the water quality parameters. To comparison data processing methods (correlation coefficient and PCA methods), the input variables of both methods were determined and GA-LSSVR was performed for each of the input variables. To compare the results of the PCA and correlation coefficient methods, some statistics were used. It is worth mentioning that according to NS criteria both input selection methods are capable to model water quality parameters. Also the results show that using correlation coefficient method lead to more accurate results than PCA.
M. Moravej; K. Khalili; J. Behmanesh
Abstract
Introduction: Studying the hydrological cycle, especially in large scales such as water catchments, is difficult and complicated despite the fact that the numbers of hydrological components are limited. This complexity rises from complex interactions between hydrological components and environment. Recognition, ...
Read More
Introduction: Studying the hydrological cycle, especially in large scales such as water catchments, is difficult and complicated despite the fact that the numbers of hydrological components are limited. This complexity rises from complex interactions between hydrological components and environment. Recognition, determination and modeling of all interactive processes are needed to address this issue, but it's not feasible for dealing with practical engineering problems. So, it is more convenient to consider hydrological components as stochastic phenomenon, and use stochastic models for modeling them. Stochastic simulation of time series models related to water resources, particularly hydrologic time series, have been widely used in recent decades in order to solve issues pertaining planning and management of water resource systems. In this study time series models fitted to the precipitation, evaporation and stream flow series separately and the relationships between stream flow and precipitation processes are investigated. In fact, the three mentioned processes should be modeled in parallel to each other in order to acquire a comprehensive vision of hydrological conditions in the region. Moreover, the relationship between the hydrologic processes has been mostly studied with respect to their trends. It is desirable to investigate the relationship between trends of hydrological processes and climate change, while the relationship of the models has not been taken into consideration. The main objective of this study is to investigate the relationship between hydrological processes and their effects on each other and the selected models.
Material and Method: In the current study, the four sub-basins of Lake Urmia Basin namely Zolachay (A), Nazloochay (B), Shahrchay (C) and Barandoozchay (D) were considered. Precipitation, evaporation and stream flow time series were modeled by linear time series. Fundamental assumptions of time series analysis namely normalization and stationarity were considered. Skewness test applied to evaluate normalization of evaporation, precipitation and stream flow time series and logarithmic transformation function executed for in order to improve normalization. Stationarity of studied time series were evaluated by well-known powerful ADF and KPSS stationarity tests. Time series model's order was determined using modified AICC test and the portmanteau goodness of fit test was used to evaluate the adequacy of developed linear time series models. Man-Kendall trend analysis was also conducted for the precipitation amount, the number of rainy days, the maximum precipitation with 24 hours duration, the evaporation and stream flow in monthly and annual time scales.
Results and Discussion: Inferring to the physical base of ARMA models provided by Salas et al (1998), the precipitation has been considered independently and stochastically. If this assumption is not true in a given basin, it is expected that the MA component of stream flow discharge model be eliminated or washed out. This case occurred in basins A, B and C. In these basins, the behavior of precipitation and evaporation was autoregressive. It was observed that the stream flow discharge behavior also follows autoregressive models that had greater lags than precipitation and evaporation lags. This result proved that the precipitation, evaporation, and stream flow processes in the basin were regular processes. In basin D, the behavior of precipitation was stochastic and followed the MA model, which was related to the stochastic processes. In this basin, the stochastic behavior of precipitation affected the stream flow behavior, and it was observed that the stochastic term of MA also appeared in the stream flow. Thus, this leads to decrease the memory of stream flow discharge. The fact that the MA component in the stream flow discharge was greater than the MA component in precipitation indicated that during the process of producing stream flow discharge from precipitation, the stochastic factors performed an important role.
Conclusion: A comprehensive investigation on hydrological time series models of precipitation, evaporation and stream flow were investigated in this study. The framework of the study consists of trend analysis using Mann-Kendall test and time series. Trend analysis results indicate the significant changes of water resources in the studied area. It means that sustainable development in studied area is greatly threatened. The results of parallel modeling of precipitation, evaporation and stream flow time series showed that the behavior of stream flow models are greatly affected by precipitation models. In other words, this study evaluate the physical concept of ARMA models in real-world monthly time scale for three main hydrologic cycle components and suggest that considering parallel hydrological time series modeling could increase the accuracy to select a model for simulation and prediction of stream flow time series. In addition, it suggested that there is a relation between climate pattern and hydrological time series models.
Keywords: ARMA models, Stationarity, Trend analysis, Water cycle components
